Skip to main content

NuSVC

#include <Skigen/SVM>

template <typename Scalar = double>
class Skigen::NuSVC(nu=0.5, kernel=Kernel::RBF, degree=3, gamma=0, coef0=0, tol=1e-3, max_passes=50, random_state=std::nullopt)

Nu-Support Vector Classification with kernels.

Solves the nu-SVM binary classification dual via a dedicated SMO variant. The nu parameter is an upper bound on the fraction of margin errors and a lower bound on the fraction of support vectors.

Mirrors the dense binary core of sklearn.svm.NuSVC.



Attributes:

  • nu : Scalar

  • kernel : Kernel

  • classes : const Eigen::VectorXi

  • support : const std::vector< Eigen::Index > &

  • n_support : int

  • intercept : Scalar


Methods

SKIGEN_PARAMS()


predict(X)


decision_function(X)

Raw decision function — sum_s dual_coef_s K(x, sv_s) + b.


fit(X, y)


predict(X)